Skip to content

Image and video settings ​

Every parameter an image or video job takes, how locked models behave, how to follow and cancel a job, how to tune a model for your machine, and the settings and limits these models share. To make something, start with Images or Video.

Image and video parameters ​

Every field but prompt is optional; anything left out comes from the model's visual block. Unknown fields are ignored. The upscaler takes its own two fields instead: see Upscaling.

Field
promptWhat to make. Text past the first few hundred tokens is not read
negative_promptWhat to steer away from. Only used above CFG 1, so at CFG 1 it is refused
width, height16 to 4096 each, and a multiple of the model's grid (32 on Wan 2.2, 64 on SDXL, LTX-2.3 and LTX-2.5): a size off it is refused with the nearest two. Quality falls away from the model's native size
stepsSampling steps, 1 to 150. More is slower, and past the model's own count rarely better
cfgGuidance, above 0 and at most 30. At 1 each step takes half the time
samplereuler, euler_a, heun, dpm++2m, lcm, ddim_trailing and others. An unknown name is refused
flow_shiftFor flow-matching video models (Wan), above 0 and at most 30
frames, fpsVideo only: length in frames, from 1 to the model's max_frames in capabilities, and frame rate (1 to 60). max_frames is the lower of what the model makes (81 for Wan 2.2 A14B, Wan 2.1 VACE and Wan 2.2 S2V, 1024 for the others) and DPPAN_VISUAL_MAX_FRAMES (481 by default). MiniMax-H3 makes 24 fps only, and refuses another. See Longer videos
extend_artifactA video you made, to continue; frames then counts what is added. See Longer videos
prompts, color_matchA longer video: a prompt per part, and how closely each holds the first's look. See Longer videos
keyframe_artifacts, keyframe_spacingA video through keyframes, and the frames between them. See Longer videos
audio, audio_artifactA video's sound: see Sound
loras[{"name": "…", "strength": 1.0}], from the model's loras/ folder. Strength from -2 to 2; below 0 pushes the other way
image_artifact, strength, fit, ref_artifacts, end_image_artifactSee Starting from an image
mask_artifactSee Changing part of an image
control_artifact, control, control_strengthWan VACE only: see Following a video
nodeWhere it runs: local, or a node's name or id. See On other machines
scaleThe upscaler only: see Upscaling

A refused request fails the job as soon as it starts, with error_codebad_params and a message naming the field. A number outside its range is refused with the range ("steps must be between 1 and 150, got 500"), never clamped. The dashboard holds its fields to the same ranges: a value outside one turns the field red, says what it takes, and Generate waits until it is fixed.

Locked models ​

Distilled models — Z-Image Turbo, Krea-2 Turbo, FLUX 3 Klein, FLUX.2 Klein, FLUX.1 schnell, SD3.5 Large Turbo, HiDream-O1 Dev, Wan 2.2 TI2V Turbo, LTX-2.3, LTX-2.5, MiniMax-H3 with Hyperflow, Pika H3 Flex, and the fast Wan 2.2 A14B, Wan 2.2 S2V, Wan VACE, Wan 2.2 VACE-Fun, Qwen-Image 2.1 and HunyuanVideo 1.5 — work well only with their own few steps at CFG 1. Their visual block says locked, and a request that sets steps, cfg, sampler or flow_shift is refused. Size, length, seed, input images and LoRAs still apply.

Progress, previews and cancelling ​

Stage
loadingThe model starts. Only on its first job, or after it was unloaded
preparingThe prompt is encoded and the model's weights read in
samplingThe model works step by step. The only stage with a fraction
decodingThe result becomes pixels. Long for a video
publishingThe PNG or MP4 is saved
waitingThe node running the job left, and the job waits for another machine with the model

While a job samples, GET /v1/generations/:id/preview returns its newest preview as a PNG (a video's middle frame), updated every step; X-Preview-Step says which. It answers 404 before the first step and after the job ends.

DELETE /v1/generations/:id stops a job within a few seconds and keeps the model loaded for the next one.

What to expect ​

Times from one machine, an Apple M5 Pro with 24 GB; yours will differ with its GPU and memory:

ModelJobTime
SDXL base 1.01024×1024, 20 steps, CFG 754 s
Z-Image Turbo1024×1024, 8 steps, first job (includes loading)69 s
Real-ESRGAN x4plusa 1024×1024 image, either scale90 s
Wan 2.2 TI2V Turbo832×480, 33 frames, from a first frame111 s
LTX-2.31024×576, 49 frames (2 s), with its sound2.3 min
LTX-2.31024×576, 97 frames (4 s), with its sound3.9 min
Wan VACE 1.3B fast832×480, 33 frames, following a video4 min
Wan 2.2 TI2V832×480, 33 frames, 20 steps, CFG 6, from a first frame5.2 min
LTX-2.31024×576, 97 frames, from a first frame, or a first and a last6–6.5 min
MiniMax-H3864×480, 22 frames, 20 steps, from a first and a last frame8.8 min
Wan VACE 1.3B832×480, 33 frames, following a video16 min

Longer and larger takes longer: the Wan 2.2 TI2V models' default is 1280×704 at 49 frames, MiniMax-H3's 39 frames, and the LTX models' 1024×576 at 97 frames. MiniMax-H3 and Wan VACE 14B need about 16 GB of free memory, LTX-2.3, LTX-2.5 and Wan 2.2 T2V A14B fast about 20 GB, Wan VACE 1.3B under 10 GB.

Tuning a model for this machine ​

An installed model's settings are the visual block of bundle.dppan.json in its directory. They are the defaults every request inherits — change them for a shorter default video, say, or to trade speed for memory:

json
"visual": {
  "kind": "video", "width": 1280, "height": 704, "frames": 49, "fps": 24,
  "sampler": "lcm", "sigmas": [1.0, 0.9375, 0.833333, 0.625, 0.0], "cfg": 1.0,
  "locked": true, "start_image": true, "params_backend": "te=disk,diffusion=disk"
}
Key
kindimage or video
width, heightThe native size, and a request's default
frames, fpsA video's default length and frame rate
frame_step, min_framesThe only lengths a model makes, when it has fixed ones: MiniMax-H3's 17 and 5 give 5, 22, 39… frames
max_framesA model that makes each clip in one go: the longest clip it was trained for (Wan: 81). A longer request is refused
steps, cfg, sampler, flow_shiftSampling defaults. 0 or absent: 20 steps, CFG 7
sigmasA distilled model's noise schedule, ending in 0. It sets the step count
refine_sigmasLTX-2.3 and LTX-2.5: the second stage's schedule, run after the video is enlarged
negative_promptThe default negative prompt
guidanceA guidance-distilled model's guidance (FLUX.1 Kontext: 2.5). Absent takes 3.5
skip_layer_guidanceSkip Layer Guidance: layers, scale, start and end (SD3.5 Medium: layers 7, 8 and 9 at 2.5, from 0.01 to 0.2)
lockedRefuse requests that change the schedule
start_image, end_image, ref_imagesWhich images a request may send
params_backendWhich parts are read in for each job, instead of kept in memory

Restart the orchestrator to apply a change. An unknown key stops the model from loading, and startup logs ignoring visual bundle … with the reason.

params_backend trades time for memory. The video models read their text encoder and video model in for each job (te=disk,diffusion=disk), about 10 s more a job, so less is held between jobs and the decode has room. LTX-2.3 and LTX-2.5 add vae=disk, so each of their jobs reads over 20 GB from disk. With plenty of memory, remove it.

Your changes survive a re-pull: dppan pull --visual keeps every value you changed and updates the rest.

LoRAs ​

A model's LoRAs go in the loras/ folder of its directory, as .safetensors or .gguf files. A request names one by its file name without the extension. The SDXL install includes sd_xl_offset_example-lora_1.0, for deeper darks and brighter lights. The folder is read at startup; capabilities lists what it found.

Memory and the worker process ​

Each image or video model runs in a process of its own. If one crashes, only its job fails, and the next job starts it again. Between jobs it stays loaded, a cancelled job included, so the next job starts sooner. After DPPAN_VISUAL_IDLE_MINUTES (10 minutes) with no job, its process stops and returns all its memory; the next job loads it again. Stopping the orchestrator stops every model's process with it.

Image, video, speech and music models share one memory budget (DPPAN_SPEECH_MEMORY_BUDGET_MB). When a job needs room, the least recently used idle model is unloaded and loads again on its next request — a small budget costs time, not failures. On a Mac, an image or video model that is loading keeps the speech models loaded, so a spoken reply during a render starts at once, unless it needs their memory.

DPPAN_VISUAL_MAX_VRAM_GIB caps the GPU memory each image or video model uses. The default, 0, takes what is free when the model starts, less 512 MiB. Set it on a machine doing other work. A negative value leaves that much free instead.

A text node on this machine, joined through localhost, is such work: with the setting unset, each image or video model here leaves room for two chat sessions on the layers that node serves, plus 1 GB, at most half the memory its model runs in. dppan join prints how much; a shorter DPPAN_CTX on the node makes each session smaller. A value set in DPPAN_VISUAL_MAX_VRAM_GIB, 0 included, is used as it is instead.

Configuration ​

VariableDefault
DPPAN_MODELS_DIR~/.dppan/modelsWhere pull installs and the orchestrator looks, in bundles/
DPPAN_VISUAL_MAX_VRAM_GIB0 (what is free)GPU memory per image or video model, in GiB
DPPAN_SPEECH_MEMORY_BUDGET_MBhalf of RAMMemory all loaded generators may hold together
HF_TOKENunsetHugging Face token for gated repositories
DPPAN_VISUAL_NODESoffon accepts nodes' image and video models (On other machines)
DPPAN_VISUAL_PREFER_NODESonJobs that name no place try nodes serving only image and video models before this machine. off tries this machine first
DPPAN_IMAGES_SYNC_TIMEOUT_SECS900How long /v1/images/generations and /v1/images/edits wait before returning a job ID to poll
DPPAN_VISUAL_MAX_FRAMES481 (20 s at 24 fps)Longest video a request may ask for, 1 to 1024. A model trained on shorter clips stops at its own length
DPPAN_VISUAL_DEADLINE_MINUTES240 (4 h)How long an image job may run, and a video for each part it is made in, 1 to 1440
DPPAN_VISUAL_IDLE_MINUTES10How long an image or video model stays loaded with no job, 1 to 1440. Then its process stops and the next job loads it again

An image or video job's time limit counts from when it starts running, so time spent waiting behind another job does not use it up. A job past it is stopped and marked expired. A request's deadline_seconds sets its own deadline instead, counted from when it is submitted. Both settings are listed under Settings → Limits in the dashboard.

Known limitations ​

  • One music, image or video job at a time on each machine. Transcriptions run beside one; spoken replies and voice cloning do on a Mac when their model fits in the memory left, and otherwise wait for it; /v1/audio/speech may then return a job ID to poll. Running image and video work on a node keeps this machine free.
  • LTX-2.3, LTX-2.5 and Wan 2.2 T2V A14B fast need about 20 GB free. On a machine short of that, run them on a node with more memory.
  • A node serving a text model and image or video models at once shares its GPU between them.
  • Only a Mac makes and reads H.264. A node that is not a Mac cannot Restyle or Extend a video made on a Mac: run that job on a Mac (Run on).
  • No watermark or signed content credentials, only the metadata label. Label generated media where you publish it; some jurisdictions require that.
  • No content filter: the model makes what the prompt asks for.
  • Wan VACE is 480p at 16 fps and follows a video from its start; it cannot extend a clip or change one region. Preparing a control video in the dashboard needs Chrome, Edge or Firefox; elsewhere, Restyle a video made here.

Free to run · Proprietary